←back to thread

534 points BlueFalconHD | 1 comments | | HN request time: 0.234s | source

I managed to reverse engineer the encryption (refered to as “Obfuscation” in the framework) responsible for managing the safety filters of Apple Intelligence models. I have extracted them into a repository. I encourage you to take a look around.
Show context
bawana ◴[] No.44484214[source]
Alexandra Ocasio Cortez triggers a violation?

https://github.com/BlueFalconHD/apple_generative_model_safet...

replies(7): >>44484242 #>>44484256 #>>44484284 #>>44484352 #>>44484528 #>>44485841 #>>44488050 #
mmaunder ◴[] No.44484284[source]
As does:

   "(?i)\\bAnthony\\s+Albanese\\b",
    "(?i)\\bBoris\\s+Johnson\\b",
    "(?i)\\bChristopher\\s+Luxon\\b",
    "(?i)\\bCyril\\s+Ramaphosa\\b",
    "(?i)\\bJacinda\\s+Arden\\b",
    "(?i)\\bJacob\\s+Zuma\\b",
    "(?i)\\bJohn\\s+Steenhuisen\\b",
    "(?i)\\bJustin\\s+Trudeau\\b",
    "(?i)\\bKeir\\s+Starmer\\b",
    "(?i)\\bLiz\\s+Truss\\b",
    "(?i)\\bMichael\\s+D\\.\\s+Higgins\\b",
    "(?i)\\bRishi\\s+Sunak\\b",
   
https://github.com/BlueFalconHD/apple_generative_model_safet...

Edit: I have no doubt South African news media are going to be in a frenzy when they realize Apple took notice of South African politicians. (Referring to Steenhuisen and Ramaphosa specifically)

replies(6): >>44484366 #>>44484419 #>>44484695 #>>44484709 #>>44484883 #>>44487192 #
echelon ◴[] No.44484709[source]
Apple's 1984 ad is so hypocritical today.

This is Apple actively steering public thought.

No code - anywhere - should look like this. I don't care if the politicians are right, left, or authoritarian. This is wrong.

replies(2): >>44484841 #>>44493486 #
avianlyric ◴[] No.44484841[source]
Why is this wrong? Applying special treatment to politically exposed persons has been standard practice in every high risk industry for a very long time.

The simple fact is that people get extremely emotional about politicians, politicians both receive obscene amounts of abuse, and have repeatedly demonstrated they’re not above weaponising tools like this for their own goals.

Seems perfectly reasonable that Apple doesn’t want to be unwittingly draw into the middle of another random political pissing contest. Nobody comes out of those things uninjured.

replies(7): >>44484868 #>>44484887 #>>44484934 #>>44484948 #>>44485015 #>>44485098 #>>44488968 #
1. raxxorraxor ◴[] No.44488968[source]
What do you mean reasonable? I know that some Apple users tend to outsource "possibilities" to their favorite company, but I would obviously want an AI to not be affected by the political bitching du jours.

Not that getting the latest trash talk is the main vocation of pretrained AIs anyway.

The only risk here is that some third grade journalist of a third grade newspaper writes another article about how outrageous some generated AI statement is. An article that should be completely ignored instead of it leading to more censorship.

And Apple flinches here, so in the end it means it cannot provide a sensible general model. It would be affected by their censorship.